Phase-change based tuning for automatic chord recognition

This paper focuses on automatic extraction of acoustic chord sequences from a piece of music. Firstly, the evaluation of a set of different windowing methods for Discrete Fourier Transform is investigated in terms of their efficiency. Then, a new tuning solution is introduced, based on a method developed in the past for phase vocoder. Pitch class profile vectors, that represent harmonic information, are extracted from the given audio signal. The resulting chord sequence is obtained by running a Viterbi decoder on trained hidden Markov models. We performed several experiments using the proposed technique. Results obtained on 175 manually-labeled songs provided an accuracy that is comparable to the state of the art